Cross-validators (CV) take a classifier (CL), a datasource (DS) and optionally feature preprocessor (FP) objects, and they run a cross-validation decoding scheme by training and testing the classifier with data generated from the datasource object (and possibly fed through the feature pre-processing first).

The Neural Decoding Toolbox comes with following classifier objects:


Methods that must be implemented

Objects that are cross-validators must implement the following method:

DECODING_RESULTS = cv.run_cv_decoding

  • This method uses a datasource (DS) to generate training and test splits of the data, optionally applies feature preprocessors (FP) to the training and test data, sends the training data to a classifier (CL) which learns the relationship between the data and the labels, and then tests the classifier using the test data generated by the datasource (note that a datasource and a classifier must be set prior to running this method). This method may repeat the cross-validation decoding procedure multiple times by generating different data splits from the datasource in order to get more robust measures of the decoding accuracy.